© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2353
    Prev
    Next
    INDEX
    Explanations

    elements of contradiction or contrast in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.29
    1.2%
    1150
    +0.10
    0.4%
    382
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.29
    0.07
    2019
    +0.10
    0.07
    1265
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.60
     intersper
    -0.90
    /***
    -0.83
     /**
    -0.82
    ⓧ
    -0.82
    
    -0.81
    <?
    -0.74
    <?
    -0.73
    //*/
    -0.72
     endow
    -0.68
    POSITIVE LOGITS
     heapq
    0.65
     Czechos
    0.60
     noting
    0.56
     hectáreas
    0.56
     citing
    0.55
     pymongo
    0.55
     epoca
    0.54
     marea
    0.54
     Meksi
    0.52
     Makassar
    0.52
    Activations Density 0.522%

    No Known Activations